This model is a 5-bit quantized version of Gemma 4 E2B instruction-tuned, prepared for the MLX machine learning framework. It enables running a powerful language model on Apple Silicon devices with reduced memory requirements. The model includes appropriate tokenizer and chat template configurations for conversational use.
Gemma 4 E2B It sits in PulseGate's Quantised & converted weights category. Efficient local execution of Gemma 4 on Apple hardware with minimal memory footprint. It is built as an open-source project for Apple MLX developers. Gemma 4 E2B It is open source under the MIT license. It ships for the web, the command line, and API.
Behind Gemma 4 E2B It is lmstudio-community, and it first shipped in 2024. Development happens publicly on GitHub with 5.2k stars and 419 commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 13 similar projects. Among its 3 catalogued features are Quantized LLM, Instruction Model, and Apple Silicon Optimized.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do